Rumor Detection with Adversarial Training and Supervised Contrastive Learning

The proliferation of rumors on social media has seriously affected personal life, even threatened social security and stability. Therefore, there is an urgent need to automatically detect rumors on social media. However, existing methods lack robustness because of high dimension and sparsity of natural language texts and one hundreds description ways of same events. In order to solve this issue, we propose a novel model ATSCL, which integrates adversarial training and supervised contrastive learning. We enhance ATSCL by adding adversarial perturbations in embedding layer to obtain a more robust model. At the same time, we also utilize a supervised contrastive learning objective which can shorten the distance between rumor samples, push away the distance between non-rumor samples, and further enhance the robustness of ATSCL. The experimental results on two real-word datasets Twitter15 and Twitter16 demonstrate that our method outperforms several state-of-the-art methods.